Graph Transformer Networks: Learning meta-path graphs to improve GNNs
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yun, Seongjun | - |
dc.contributor.author | Jeong, Minbyul | - |
dc.contributor.author | Yoo, Sungdong | - |
dc.contributor.author | Lee, Seunghun | - |
dc.contributor.author | Yi, Sean S. | - |
dc.contributor.author | Kim, Raehyun | - |
dc.contributor.author | Kang, Jaewoo | - |
dc.contributor.author | Kim, Hyunwoo J. | - |
dc.date.accessioned | 2022-08-10T10:40:28Z | - |
dc.date.available | 2022-08-10T10:40:28Z | - |
dc.date.created | 2022-08-10 | - |
dc.date.issued | 2022-09 | - |
dc.identifier.issn | 0893-6080 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/142726 | - |
dc.description.abstract | Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. To address these limitations, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which preclude noisy connections and include useful connections (e.g., meta-paths) for tasks, while learning effective node representations on the new graphs in an end-to-end fashion. We further propose enhanced version of GTNs, Fast Graph Transformer Networks (FastGTNs), that improve scalability of graph transformations. Compared to GTNs, FastGTNs are up to 230x and 150x faster in inference and training, and use up to 100x and 148x less memory while allowing the identical graph transfor-mations as GTNs. In addition, we extend graph transformations to the semantic proximity of nodes allowing non-local operations beyond meta-paths. Extensive experiments on both homogeneous graphs and heterogeneous graphs show that GTNs and FastGTNs with non-local operations achieve the state-of-the-art performance for node classification tasks. The code is available: https://github.com/ seongjunyun/Graph_Transformer_Networks. (C) 2022 The Authors. Published by Elsevier Ltd. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Graph Transformer Networks: Learning meta-path graphs to improve GNNs | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Hyunwoo J. | - |
dc.identifier.doi | 10.1016/j.neunet.2022.05.026 | - |
dc.identifier.scopusid | 2-s2.0-85132351038 | - |
dc.identifier.wosid | 000823104800003 | - |
dc.identifier.bibliographicCitation | NEURAL NETWORKS, v.153, pp.104 - 119 | - |
dc.relation.isPartOf | NEURAL NETWORKS | - |
dc.citation.title | NEURAL NETWORKS | - |
dc.citation.volume | 153 | - |
dc.citation.startPage | 104 | - |
dc.citation.endPage | 119 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Neurosciences & Neurology | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Neurosciences | - |
dc.subject.keywordAuthor | GraphNeuralNetworks | - |
dc.subject.keywordAuthor | Heterogeneousgraphs | - |
dc.subject.keywordAuthor | Machinelearningongraphs | - |
dc.subject.keywordAuthor | Networkanalysis | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.